Merge branch 'main' into depr-select_dtypes-object

Author: jbrockmendel

doc/source/whatsnew/v3.0.0.rst

@@ -875,6 +875,7 @@ Other Removals
 - Removed the ``method`` keyword in ``ExtensionArray.fillna``, implement ``ExtensionArray._pad_or_backfill`` instead (:issue:`53621`)
 - Removed the attribute ``dtypes`` from :class:`.DataFrameGroupBy` (:issue:`51997`)
 - Enforced deprecation of ``argmin``, ``argmax``, ``idxmin``, and ``idxmax`` returning a result when ``skipna=False`` and an NA value is encountered or all values are NA values; these operations will now raise in such cases (:issue:`33941`, :issue:`51276`)
+- Enforced deprecation of storage option "pyarrow_numpy" for :class:`StringDtype` (:issue:`60152`)
 - Removed specifying ``include_groups=True`` in :class:`.DataFrameGroupBy.apply` and :class:`.Resampler.apply` (:issue:`7155`)
 
 .. ---------------------------------------------------------------------------

pandas/core/arrays/string_.py

@@ -167,21 +167,6 @@ def __init__(
                 else:
                     storage = "python"
 
-        if storage == "pyarrow_numpy":
-            # TODO: Enforce in 3.0 (#60152)
-            warnings.warn(
-                "The 'pyarrow_numpy' storage option name is deprecated and will be "
-                'removed in pandas 3.0. Use \'pd.StringDtype(storage="pyarrow", '
-                "na_value=np.nan)' to construct the same dtype.\nOr enable the "
-                "'pd.options.future.infer_string = True' option globally and use "
-                'the "str" alias as a shorthand notation to specify a dtype '
-                '(instead of "string[pyarrow_numpy]").',
-                FutureWarning,  # pdlint: ignore[warning_class]
-                stacklevel=find_stack_level(),
-            )
-            storage = "pyarrow"
-            na_value = np.nan
-
         # validate options
         if storage not in {"python", "pyarrow"}:
             raise ValueError(
@@ -280,9 +265,6 @@ def construct_from_string(cls, string) -> Self:
             return cls(storage="python")
         elif string == "string[pyarrow]":
             return cls(storage="pyarrow")
-        elif string == "string[pyarrow_numpy]":
-            # this is deprecated in the dtype __init__, remove this in pandas 3.0
-            return cls(storage="pyarrow_numpy")
         else:
             raise TypeError(f"Cannot construct a '{cls.__name__}' from '{string}'")
 

pandas/core/config_init.py

@@ -478,12 +478,6 @@ def is_valid_string_storage(value: Any) -> None:
     legal_values = ["auto", "python", "pyarrow"]
     if value not in legal_values:
         msg = "Value must be one of python|pyarrow"
-        if value == "pyarrow_numpy":
-            # TODO: we can remove extra message after 3.0
-            msg += (
-                ". 'pyarrow_numpy' was specified, but this option should be "
-                "enabled using pandas.options.future.infer_string instead"
-            )
         raise ValueError(msg)
 
 

pandas/core/ops/docstrings.py

@@ -435,8 +435,10 @@ def make_flex_doc(op_name: str, typ: str) -> str:
 
 Parameters
 ----------
-other : Series or scalar value
-    The second operand in this operation.
+other : object
+    When a Series is provided, will align on indexes. For all other types,
+    will behave the same as ``==`` but with possibly different results due
+    to the other arguments.
 level : int or name
     Broadcast across a level, matching Index values on the
     passed MultiIndex level.

pandas/core/series.py

@@ -6092,8 +6092,10 @@ def eq(
 
         Parameters
         ----------
-        other : Series or scalar value
-            The second operand in this operation.
+        other : object
+            When a Series is provided, will align on indexes. For all other types,
+            will behave the same as ``==`` but with possibly different results due
+            to the other arguments.
         level : int or name
             Broadcast across a level, matching Index values on the
             passed MultiIndex level.
@@ -6161,8 +6163,10 @@ def le(self, other, level=None, fill_value=None, axis: Axis = 0) -> Series:
 
         Parameters
         ----------
-        other : Series or scalar value
-            The second operand in this operation.
+        other : object
+            When a Series is provided, will align on indexes. For all other types,
+            will behave the same as ``==`` but with possibly different results due
+            to the other arguments.
         level : int or name
             Broadcast across a level, matching Index values on the
             passed MultiIndex level.
@@ -6233,8 +6237,10 @@ def ge(self, other, level=None, fill_value=None, axis: Axis = 0) -> Series:
 
         Parameters
         ----------
-        other : Series or scalar value
-            The second operand in this operation.
+        other : object
+            When a Series is provided, will align on indexes. For all other types,
+            will behave the same as ``==`` but with possibly different results due
+            to the other arguments.
         level : int or name
             Broadcast across a level, matching Index values on the
             passed MultiIndex level.

pandas/tests/arrays/string_/test_string.py

@@ -61,14 +61,6 @@ def string_dtype_highest_priority(dtype1, dtype2):
     return DTYPE_HIERARCHY[max(h1, h2)]
 
 
-def test_dtype_constructor():
-    pytest.importorskip("pyarrow")
-
-    with tm.assert_produces_warning(FutureWarning):
-        dtype = pd.StringDtype("pyarrow_numpy")
-    assert dtype == pd.StringDtype("pyarrow", na_value=np.nan)
-
-
 def test_dtype_equality():
     pytest.importorskip("pyarrow")
 

pandas/tests/extension/test_string.py

@@ -116,8 +116,7 @@ def test_eq_with_str(self, dtype):
             # only the NA-variant supports parametrized string alias
             assert dtype == f"string[{dtype.storage}]"
         elif dtype.storage == "pyarrow":
-            with tm.assert_produces_warning(FutureWarning):
-                assert dtype == "string[pyarrow_numpy]"
+            assert dtype == "str"
 
     def test_is_not_string_type(self, dtype):
         # Different from BaseDtypeTests.test_is_not_string_type

pandas/tests/series/methods/test_compare.py

@@ -1,3 +1,8 @@
+from enum import (
+    Enum,
+    auto,
+)
+
 import numpy as np
 import pytest
 
@@ -138,3 +143,61 @@ def test_compare_datetime64_and_string():
     tm.assert_series_equal(result_eq1, expected_eq)
     tm.assert_series_equal(result_eq2, expected_eq)
     tm.assert_series_equal(result_neq, expected_neq)
+
+
+def test_eq_objects():
+    # GH#62191 Test eq with Enum and List elements
+
+    class Thing(Enum):
+        FIRST = auto()
+        SECOND = auto()
+
+    left = pd.Series([Thing.FIRST, Thing.SECOND])
+    py_l = [Thing.FIRST, Thing.SECOND]
+
+    result = left.eq(Thing.FIRST)
+    expected = pd.Series([True, False])
+    tm.assert_series_equal(result, expected)
+
+    result = left.eq(py_l)
+    expected = pd.Series([True, True])
+    tm.assert_series_equal(result, expected)
+
+    result = left.eq(np.asarray(py_l))
+    expected = pd.Series([True, True])
+    tm.assert_series_equal(result, expected)
+
+    result = left.eq(pd.Series(py_l))
+    expected = pd.Series([True, True])
+    tm.assert_series_equal(result, expected)
+
+    result = pd.Series([[1, 2], [3, 4]]).eq([1, 2])
+    expected = pd.Series([True, False])
+    with pytest.raises(AssertionError):
+        tm.assert_series_equal(result, expected)
+    expected = pd.Series([False, False])
+    tm.assert_series_equal(result, expected)
+
+
+def test_eq_with_index():
+    # GH#62191 Test eq with non-trivial indices
+    left = pd.Series([1, 2], index=[1, 0])
+    py_l = [1, 2]
+
+    # assuming Python list has the same index as the Series
+    result = left.eq(py_l)
+    expected = pd.Series([True, True], index=[1, 0])
+    tm.assert_series_equal(result, expected)
+
+    # assuming np.ndarray has the same index as the Series
+    result = left.eq(np.asarray(py_l))
+    expected = pd.Series([True, True], index=[1, 0])
+    tm.assert_series_equal(result, expected)
+
+    result = left.eq(pd.Series(py_l))
+    expected = pd.Series([False, False])
+    tm.assert_series_equal(result, expected)
+
+    result = left.eq(pd.Series([2, 1]))
+    expected = pd.Series([True, True])
+    tm.assert_series_equal(result, expected)